Hand Gesture Shape Descriptor Based on Energy-Ratio and Normalized Fourier Transform Coefficients

The hand gesture shape is the most remarkable feature for gesture recognition system. Since hand gesture is diversity, polysemy, complex deformation and spatio-temporal difference, the hand gesture shape descriptor is a challenging problem for gesture recognition. This paper presents a hand gesture shape describing method based on energy-ratio and normalized Fourier descriptors. Firstly, the hand gesture contour of the input image is extracted by YCb’Cr’ ellipse skin color model. Secondly, the Fourier coefficients of the contour are calculated to transform the point sequence of the contour to frequency domain. Then the Fourier coefficients are normalized to meet the rotation, translation, scaling and curve origin point invariance. Finally, the items of normalized Fourier coefficients are selected by calculating energy-ratio information as the hand shape descriptors. For validating the shape descriptors performance, the hand gestures 1-10 are recognized with the template matching method and the shape descriptor method, respectively. The experiment results show that the method can well describe the hand shape information and are higher recognition rate.

[1]  Michal Kawulok,et al.  Fast propagation-based skin regions segmentation in color images , 2013, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).

[2]  Wenjun Tan,et al.  Gesture segmentation based on YCb'Cr' color space ellipse fitting skin color modeling , 2012, 2012 24th Chinese Control and Decision Conference (CCDC).

[3]  Alicja Wakulicz-Deja,et al.  Man-Machine Interactions 3, Proceedings of the 3rd International Conference on Man-Machine Interactions, ICMMI 2013, Brenna, Poland, October 22-25, 2013 , 2014, ICMMI.

[4]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[5]  Sim Heng Ong,et al.  Image retrieval based on multidimensional feature properties , 1995, Electronic Imaging.

[6]  Ting-Chuen Pong,et al.  Computer Vision — ACCV'98 , 1998, Lecture Notes in Computer Science.

[7]  Jianning Xu.  Morphological Decomposition of 2-D Binary Shapes Into Modestly Overlapped Octagonal and Disk Components , 2007, IEEE Transactions on Image Processing.

[8]  Fabrice Druaux,et al.  Particles shape analysis and classification using the wavelet transform , 2000, Pattern Recognit. Lett..

[9]  Re Gonzalez,et al.  R.C. Eddins, Digital image processing using MATLAB, vol. Gatesmark Publishing Knoxville , 2009 .

[10]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[11]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[12]  P. H. Lewis,et al.  2D shape signature based on fractal measurements , 1994 .

[13]  King-Sun Fu,et al.  Shape Discrimination Using Fourier Descriptors , 1977, IEEE Trans. Syst. Man Cybern..

[14]  Alexander H. Waibel,et al.  Skin-Color Modeling and Adaptation , 1998, ACCV.

[15]  Mohammad R. Sayeh,et al.  A neural network approach to robust shape classification , 1990, Pattern Recognit..

[16]  Wang Tao.  USING FOURIER DESCRIPTORS TO RECOGNIZE OBJECT'S SHAPE , 2002 .

[17]  Jakub Nalepa,et al.  Wrist Localization in Color Images for Hand Gesture Recognition , 2013, ICMMI.

[18]  Anil K. Jain,et al.  Face Detection in Color Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Elli Angelopoulou,et al.  Understanding the color of human skin , 2001, IS&T/SPIE Electronic Imaging.